Shuang Li

Assistant Professor School of Data Science The Chinese University of Hong Kong (Shenzhen) Daoyuan Building, 508b Shenzhen, Guangdong, China Email: lishuang@cuhk.edu.cn [Google Scholar] [Curriculum Vitae]

About me

I am an Assistant Professor in the School of Data Science at The Chinese University of Hong Kong (Shenzhen). Previously, I was a postdoctoral fellow at Harvard University, working on mobile health with Prof. Susan Murphy. I earned my Ph.D. in Industrial Engineering from the H. Milton Stewart School of Industrial & Systems Engineering at Georgia Tech in 2019, and earlier, I received B.E. in Automation from the University of Science and Technology of China in 2011.

Research Interests

My research delves into the development of knowledge-enhanced sequential models and sequential decision tools, which prioritize interpretability and trustworthiness in machine learning. More specifically, my research focuses on:

• Knowledge-Enhanced Sequential Models: By integrating domain-specific knowledge into machine learning algorithms, we aim to facilitate transparent decision-making processes and to create robust and reliable frameworks applicable in high-stakes systems.

• Human Cognitive Process Modeling: By incorporating Theory of Mind and spatial-temporal logical reasoning into AI systems, we aim to enable effective collaboration between humans and AI.

• Applications in Healthcare: We aim to apply machine learning tools to improve healthcare policies, clinical workflows, and patient outcomes through informed decision-making.

Publications

Conference

• Beyond Accuracy: Latent Perturbations for Cognitive-Aware Diagnosis.
  Y. Yan, Y. Fu, W. Ren, H. Gao and S. Li.
  International Conference on Machine Learning (ICML), 2026.

  • Best Paper Award at NeurIPS GenAI4Health Workshop, 2025

• Branching Diffusion for Point Processes in Time and Space.
  C. Yang, W. Shen and S. Li.
  International Conference on Machine Learning (ICML), 2026.

• Forward-Chaining Temporal Point Process.
  C. Yang, W. Ren and S. Li.
  International Conference on Machine Learning (ICML), 2026.

• Neural Assortment Optimization.
  Z. Yang, J. Liang, Z. Wang, Y. An, R. Gao and S. Li.
  ACM Conference on Economics and Computation (EC), 2026.

• Learning Human Habits with Rule-Guided Active Inference.
  Z. Gong, C. Yang, W. Ren and S. Li.
  International Conference on Learning Representations (ICLR), 2026.

• Inferring the Invisible: Neuro-Symbolic Rule Discovery for Missing Value Imputation.
  W. Ren, K. Wan, J. Leng and S. Li.
  International Conference on Learning Representations (ICLR), 2026.

• Sampling Complexity of TD and PPO in RKHS.
  L. Zou, W. Ren, W. Zhang, L. Ding and S. Li.
  International Conference on Learning Representations (ICLR), 2026.

• From Counts to Preferences: Preference-Driven Models for Spatio-Temporal Event Data.
  C. Yang, Y. Kuang and S. Li.
  International Conference on Artificial Intelligence and Statistics (AISTATS), 2026.

• Deliberate-When-Needed: Flow-Reasoner for Neuro-Symbolic Continuous Thought.
  W. Shen, B. Li, C. Yang and S. Li.
  International Conference on Artificial Intelligence and Statistics (AISTATS), 2026.

• DeepHalo: A Neural Choice Model with Controllable Context Effects.
  S. Zhang, Z. Wang, R. Gao and S. Li.
  Neural Information Processing Systems (NeurIPS), 2025. (Spotlight)

• RKHS Choice Model.
  Y. Yang, Z. Wang, R. Gao and S. Li.
  ACM Conference on Economics and Computation (EC), 2025.

  • Finalist of 2025 INFORMS Undergraduate Operations Research Award

• Flow-Based Delayed Hawkes Process.
  C. Yang, W. Ren and S. Li.
  Conference on Uncertainty in Artificial Intelligence (UAI), 2025.

• Evolving Minds: Logic-Informed Inference from Temporal Action Patterns.
  C. Yang, S. Cui, Y. Yang and S. Li.
  International Conference on Machine Learning (ICML), 2025.

• Convergence of Mean-Field Langevin Stochastic Descent-Ascent for Distributional Minimax Optimization.
  Z. Liu, F. Liu, R. Gao and S. Li.
  International Conference on Machine Learning (ICML), 2025. (Spotlight)

• Logic-Logit: A Logic-Based Approach to Choice Modeling.
  S. Zhang, W. Ren and S. Li.
  International Conference on Learning Representations (ICLR), 2025.

• HyperLogic: Enhancing Diversity and Accuracy in Rule Learning with HyperNets.
  Y. Yang, W. Ren and S. Li.
  Neural Information Processing Systems (NeurIPS), 2024.

• Neuro-Symbolic Temporal Point Processes.
  Y. Yang, C. Yang, B. Li, Y. Fu and S. Li.
  International Conference on Machine Learning (ICML), 2024.

• Latent Logic Tree Extraction for Event Sequence Explanation from LLMs.
  Z. Song, C. Yang, C. Wang, B. An and S. Li.
  International Conference on Machine Learning (ICML), 2024.

• Unveiling Latent Causal Rules: A Temporal Point Process Approach for Abnormal Event Explanation.
  Y. Kuang, C. Yang, Y. Yang and S. Li.
  International Conference on Artificial Intelligence and Statistics (AISTATS), 2024.

• Enhancing Human-AI Collaboration Through Logic-Guided Reasoning.
  C. Cao, Y. Fu, S. Xu, R. Zhang and S. Li.
  International Conference on Learning Representations (ICLR), 2024.

• Amortized Network Intervention to Steer Excitatory Point Processes.
  Z. Song, W. Ren and S. Li.
  International Conference on Learning Representations (ICLR), 2024.

• Discovering Intrinsic Spatial-Temporal Logic Rules to Explain Human Actions.
  C. Cao, C. Yang, R. Zhang and S. Li.
  Neural Information Processing Systems (NeurIPS), 2023.

• Explaining Point Processes by Learning Interpretable Temporal Logic Rules.
  S. Li, M. Feng, L. Wang, A. Essofi, Y. Cao, J. Yan and L. Song.
  International Conference on Learning Representations (ICLR), 2022.

• Temporal Logic Point Processes.
  S. Li, L. Wang, R. Zhang, X. Chang, X. Liu, Y. Xie, Y. Qi, and L. Song.
  International Conference on Machine Learning (ICML), 2020.

• Continuous-Time Dynamic Graph Learning via Neural Interaction Processes.
  X. Chang, X. Liu, J. Wen, S. Li, Y. Fang, L. Song, and Y. Qi.
  The Conference on Information and Knowledge Management (CIKM), 2020.

• Generative Adversarial User Model for Reinforcement Learning Based Recommendation System.
  X. Chen, S. Li, H. Li, S. Jiang, Y. Qi, and L. Song.
  International Conference on Machine Learning (ICML), 2019.

• Learning Temporal Point Processes via Reinforcement Learning.
  S. Li, S. Xiao, S. Zhu, N. Du, Y. Xie, and L. Song.
  Neural Information Processing Systems (NeurIPS), 2018. (Spotlight)

• Recurrent Hidden Semi-Markov Model.
  H. Dai, B. Dai, Y. Zhang, S. Li, and L. Song.
  International Conference on Learning Representations (ICLR), 2017.

• Fake News Mitigation via Point Processes Based Intervention.
  M. Farajtabar, J. Yang, X. Ye, R. Trivedi, E. Khalil, S. Li, H. Xu, L. Song, and H. Zha.
  International Conference on Machine Learning (ICML), 2017.

• Online Seismic Event Picking Via Sequential Change-Point Detection.
  S. Li, Y. Cao, C. Leamon, Y. Xie, L. Shi, and W. Song.
  Allerton Conference on Control, Communications and Computing (Allerton), 2016.

• M-Statistic for Kernel Change-Point Detection.
  S. Li, Y. Xie, H. Dai, and L. Song.
  Neural Information Processing Systems (NIPS), 2015.

• Efficient Learning of Continuous-Time Hidden Markov Models for Disease Progression.
  Y. Liu, S. Li, F. Li, L. Song, and J. Rehg.
  Neural Information Processing Systems (NIPS), 2015.

• COEVOLVE: A Joint Point Process Model for Information Diffusion and Network Co-evolution.
  M. Farajtabar, Y. Wang, M. Gomez-Rodriguez, S. Li, H. Zha, and L. Song.
  Neural Information Processing Systems (NIPS), 2015. (Oral)

Workshop

• When Agreement Becomes Unsafe: Loss-Aware Energy Control for Diagnostic Deliberation.
  Y. Yan, Y. Fu, H. Gao, T. Zhang, A. Liu and S. Li.
  ICML Workshop on Failure Modes of Agentic AI, 2026. (Oral)

• Dual-Resolution Recursive Energy: Certified Contract–Expand Inference for Sequential Decision Making.
  H. Gao, J. Zeng, W. Ren, Y. Liu and S. Li.
  ICML Workshop on Compositional Learning: Safety, Interpretability, and Agents, 2026.

• Learning What’s Missing: Failure-Driven Skill Discovery via Predicate Bridges.
  Y. Liu, W. Ren, H. Gao and S. Li.
  ICML Workshop on Compositional Learning: Safety, Interpretability, and Agents, 2026.

• Unanchoring the Mind: DAE-Guided Counterfactual Reasoning for Rare Disease Diagnosis.
  Y. Yan, Y. Fu, W. Ren and S. Li.
  NeurIPS Workshop on GenAI4Health, 2025. (Oral, Best Paper Award)

• Neural Decision Rule for Constrained Contextual Stochastic Optimization.
  Z. Liu, Z. Xu, F. Liu, R. Gao and S. Li.
  NeurIPS Workshop on MLxOR, 2025. (Spotlight)

• From Counts to Choice: Choice-Driven Spatial-Temporal Counting Process Models.
  C. Yang, Y. Kuang and S. Li.
  NeurIPS Workshop on UrbanAI: Harnessing Artificial Intelligence for Smart Cities, 2025.

• Who Should Be Consulted? Targeted Expert Selection for Rare Disease Diagnosis.
  Y. Fu, C. Yang, X. Chen, Y. Yan and S. Li.
  ICML Workshop on Collaborative and Federated Agentic Workflows, 2025. (Oral)

• Inferring the Invisible: Neuro-Symbolic Rule Discovery for Missing Value Imputation.
  W. Ren, K. Wan, J. Leng and S. Li.
  ICML Workshop on DataWorld: Unifying Data Curation Frameworks Across Domains, 2025.

• Deep Context-Dependent Choice Model.
  S. Zhang, Z. Wang, R. Gao and S. Li.
  ICML Workshop on Models of Human Feedback for AI Alignment, 2025. (Oral)

• Discovering Logic-Informed Intrinsic Rewards to Explain Human Policies.
  C. Cao, Y. Fu, C. Yang and S. Li.
  ICML Workshop on Programmatic Representations for Agent Learning, 2025.

• Counterfactual Optimization of Treatment Policies Based on Temporal Point Processes.
  Z. Jing, C. Yang and S. Li.
  ICML Workshop on Interpretable Machine Learning in Healthcare, 2023.

• Reinforcement Temporal Logic Rule Learning to Explain the Generating Processes of Events.
  C. Yang, L. Wang, Z. Mou and S. Li.
  ICML Workshop on Interpretable Machine Learning in Healthcare, 2022.

• Interpretable Deep Generative Spatio-Temporal Point Processes.
  S. Zhu, S. Li, Z. Peng, and Y. Xie.
  NeurIPS Workshop on AI for Earth Sciences, 2020. (Spotlight)

• Temporal Logic Point Processes Processes.
  S. Li, L. Wang, R. Zhang, Y. Xie, N. Du, and L. Song.
  NeurIPS Workshop on Learning with Temporal Point Processes, 2019. (Oral)

• Co-evolutionary Dynamics of Information Diffusion and Network Structure.
  M. Farajtabar, M. Gomez-Rodriguez, Y. Wang, S. Li, H. Zha, and L. Song.
  Workshop on Activity and Events in Networks: Models, Methods Applications, in conjunction with WWW, 2015.

Journal

• Neural Dynamic Portfolio Control with Provable Learning Guarantees.
  I. McPherson, Y. Huang, R. Gao, S. Li and L. Zhang.
  major revision at Management Science

• Neural-Network Mixed Logit Choice Model: Statistical and Optimality Guarantees.
  Z. Wang, R. Gao and S. Li.
  major revision at Management Science

  • Second Place, POMS-HK Best Student Paper Award.

• Micro-Randomized Trials for Promoting Engagement in Mobile Health Data Collection: Adolescent/Young Adult Oral Chemotherapy Adherence as an Example.
  S. Li, A. Psihogios, E. McKelvey, A. Ahmed, M. Rabbi, and S. Murphy.
  Current Opinion in Systems Biology, 2020.

• Scan B-statistic for Kernel Change-point Detection.
  S. Li, Y. Xie, H. Dai, and L. Song.
  Sequential Analysis, 38(4):503–544, 2019.

  • Finalist of 2018 INFORMS QSR Best Student Paper Competition

• Detecting Changes in Dynamic Events over Networks.
  S. Li, Y. Xie, M. Farajtabar, A. Verma, and L. Song.
  IEEE Transactions on Signal and Information Processing over Networks, Vol. 3, No. 2, June 2017.

  • Finalist of 2018 INFORMS Social Media Analytics Best Student Paper Competition

• COEVOLVE: A Joint Point Process Model for Information Diffusion and Network Co-evolution.
  M. Farajtabar, Y. Wang, M. Gomez-Rodriguez, S. Li, H. Zha, and L. Song.
  Journal of Machine Learning Research, 2017.

• Control for Time-Varying Delay Systems by Integrating Semi-Discretization and Hysteresis-Based Switching.
  C. Shao, S. Li, H. Li, and J. Sheng.
  Asian Journal of Control, 2018.

• COEVOLVE: A Joint Point Process Model for Information Diffusion and Network Co-evolution.
  M. Farajtabar, Y. Wang, M. Gomez-Rodriguez, S. Li, H. Zha, and L. Song.
  The Web Conference, Journal Track, 2018.

• Reinforcement Learning of Spatio-Temporal Point Processes.
  S. Zhu, S. Li, Z. Peng, and Y. Xie.
  IEEE Transactions on Knowledge and Data Engineering, 2022.

Book Chapter

• Learning Continuous-Time Hidden Markov Models for Event Data.
  Y. Liu, A. Moreno, S. Li, F. Li, L. Song, and J. Rehg.
  In Mobile Health, Springer, 2017.

Students

Doctoral Students

• Chao Yang (2022 Fall -)

  • Shandong University; Master at University of Edinburgh

  • First-author papers: ICML 2025, UAI 2025, AISTATS 2026, ICML 2026 (two papers)

• Wendi Ren (2023 Fall -)

  • Sun Yat-sen University; Master at Georgia Institute of Technology

  • First-author paper: ICLR 2026; Second-author papers: ICLR 2024, ICLR 2025, NeurIPS 2024, ICML 2026

• Yanwen Liu (2025 Fall -)

  • Beihang University

• Yuting Yan (2026 Spring -)

  • Beihang University;

  • First-author paper: ICML 2026

Research Assistants

• Chengzhi Cao (2022 Dec - 2024 Jan)

  • Visiting student from the University of Science and Technology of China

  • Initial placement: PhD in ECE at CMU

  • First-author paper: NeurIPS 2023, ICLR 2024

• Zitao Song (2022 Jun - 2023 May)

  • Master student at CUHK(SZ)

  • Initial placement: PhD in CS at Purdue University

  • First-author paper: ICLR 2024, ICML 2024

• Yang Yang (2022 Oct - 2024 Aug)

  • Master student at CUHK(SZ)

  • Initial placement: PhD at the Hong Kong University of Science and Technology (Guangzhou)

  • First-author paper: ICML 2024, NeurIPS 2024

• Yinghao Fu (2023 May - 2024 Aug)

  • Master student at CUHK(SZ)

  • Initial placement: PhD student in Data Science at the City University of Hong Kong

  • Co-first-author paper: ICLR 2024

• Shuting Cui (2023 July - 2023 Dec)

  • Initial placement: PhD at Hong Kong University of Science and Technology (Guangzhou)

  • Second-author paper: ICML 2025

• Zhiren Gong (2025 March - 2025 Aug)

  • Initial placement: PhD at Nanyang Technological University

  • First-author paper: ICLR 2026

• Yuting Yan (2025 Jan - 2025 Dec)

  • Beihang University

  • Master student at CUHK(SZ)

  • Initial placement: PhD at The Chinese University of Hong Kong, Shenzhen

  • First-author paper: NeurIPS 2025 GenAI4Health Workshop (Best Paper Award)

• Wenjie Shen (2025 Aug -)

  • University of Science and Technology of China

  • First-author paper: AISTATS 2026

• Haozhou Gao (2025 Sep -)

  • Sichuan University

  • Master student at CUHK(SZ)

Undergraduate Students at CUHK(SZ)

• Minghao Mou (2022 Jun - 2023 May)

  • Initial placement: PhD in ECE at Purdue University

• Yiling Kuang (2022 Sep - 2023 May)

  • Initial placement: PhD in Statistics at The Chinese University of Hong Kong

  • First-author paper: AISTATS 2024

• Zhaner Mou (2021 Dec - 2022 May)

  • Initial placement: Master in Biostatistics at UC San Diego

  • Current placement: PhD in Data Science at UC San Diego

• Zilin Jing (2022 May - 2023 May)

  • Initial placement: PhD in CS at Columbia University

  • First-author paper: ICML 2023 Interpretable ML in Healthcare Workshop

• Junyu Leng (2024 Jan - 2025 May)

  • Initial placement: PhD in ISE at Texas A&M

• Shuhan Zhang (2024 March - 2026 May)

  • First-author paper: ICLR 2025, NeurIPS 2025 (Spotlight)

  • Initial placement: PhD in ML at GaTech

Teaching

Graduate Level

• DDA 6060/CSC 6022 Machine Learning

  • Fall 2025, Spring 2025, Spring 2024, Spring 2023, Spring 2022

• CSC 6137 Generative Models

  • Fall 2023

• DDA 6107 Advanced Machine Learning

  • Fall 2022

Undergraduate Level

• DDA 2001 Introduction to Data Science

  • Spring 2026, Spring 2025, Spring 2024，Fall 2021

Service

• Area Chair for ICML, NeurIPS, ICLR.

• Action Editor for TMLR